Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     unui
    0.50
     তাহারা
    0.49
     isang
    0.47
     Normalmente
    0.44
     Nucleaires
    0.43
    一般来说
    0.42
     unei
    0.42
     Lieblings
    0.42
     Cient
    0.41
    ግኘት
    0.41
    POSITIVE LOGITS
     those
    0.79
     these
    0.73
     his
    0.71
     aspects
    0.64
    <unused2197>
    0.63
     their
    0.61
     фаразы
    0.55
     what
    0.54
    <unused2204>
    0.54
    <unused2169>
    0.53
    Act Density 2.923%

    No Known Activations